Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5011 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.3014. Min Act: -0.1700
Data Index: 1914996 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.3014. Min Act: -0.1700
Data Index: 1578989 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.2702. Min Act: -0.1700
Data Index: 265536 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.2702. Min Act: -0.1700
Data Index: 2081801 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.1764. Min Act: -0.1700
Data Index: 7003511 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.1139. Min Act: -0.1700
Data Index: 5588107 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.1452. Min Act: -0.1700
Data Index: 5879933 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3014. Min Range: -7.3014
Max Act: 7.0514. Min Act: -0.1700
Data Index: 7708089 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9889. Min Act: -0.1700
Data Index: 5240874 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 2106386 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9889. Min Act: -0.1700
Data Index: 5789617 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 7839333 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 8546739 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 6033083 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 5312362 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 4702353 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.9264. Min Act: -0.1700
Data Index: 4399100 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.8639. Min Act: -0.1700
Data Index: 7122819 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.8639. Min Act: -0.1700
Data Index: 2804894 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3014. Min Range: -7.3014
Max Act: 6.8327. Min Act: -0.1700
Data Index: 6642226 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19